{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VKNGJ2B624RTXFN3ZEEHCQDFES","short_pith_number":"pith:VKNGJ2B6","canonical_record":{"source":{"id":"1703.07939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T05:22:22Z","cross_cats_sorted":[],"title_canon_sha256":"79039e69298b348ec4db8f442d23b869bbea26b418c36a25afec2f2320de733e","abstract_canon_sha256":"646ffd1dee9e63b62cc471efa3bd11ccb43805dc58a58bf3aa1b5a4bd8273028"},"schema_version":"1.0"},"canonical_sha256":"aa9a64e83ed7233b95bbc9087140652496a20ace6e26fb515c13ddfa2ba3fa28","source":{"kind":"arxiv","id":"1703.07939","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07939","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07939v2","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07939","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"pith_short_12","alias_value":"VKNGJ2B624RT","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VKNGJ2B624RTXFN3","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VKNGJ2B6","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VKNGJ2B624RTXFN3ZEEHCQDFES","target":"record","payload":{"canonical_record":{"source":{"id":"1703.07939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T05:22:22Z","cross_cats_sorted":[],"title_canon_sha256":"79039e69298b348ec4db8f442d23b869bbea26b418c36a25afec2f2320de733e","abstract_canon_sha256":"646ffd1dee9e63b62cc471efa3bd11ccb43805dc58a58bf3aa1b5a4bd8273028"},"schema_version":"1.0"},"canonical_sha256":"aa9a64e83ed7233b95bbc9087140652496a20ace6e26fb515c13ddfa2ba3fa28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:35.874309Z","signature_b64":"A1eo38biPTEkL2nw6crPyCYBy6g6tFR5e0WELrf9IoevW1LUNm3NsYcgCjJtPUPzMp7Sd+OK+KEWaurDbSetDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa9a64e83ed7233b95bbc9087140652496a20ace6e26fb515c13ddfa2ba3fa28","last_reissued_at":"2026-05-18T00:38:35.873908Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:35.873908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.07939","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TqdgTWgTEUonrgX/txhjYgVp0WJ4P8bXY0y/x+eZx+Hlo3QleS4Pj7j9J0a6JepykQi10DlWwUaFFolqpBwBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:39:22.901783Z"},"content_sha256":"0912e9809fdc704b7bcfdab2b19fb0b4375cb5db224863709f8e145a79615f0a","schema_version":"1.0","event_id":"sha256:0912e9809fdc704b7bcfdab2b19fb0b4375cb5db224863709f8e145a79615f0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VKNGJ2B624RTXFN3ZEEHCQDFES","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Multimodal Interaction for Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Chenxi Liu, Jimei Yang, Xiaohui Shen, Xin Lu, Zhe Lin","submitted_at":"2017-03-23T05:22:22Z","abstract_excerpt":"In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment images by combining these two types of representations. We argue that learning word-to-image interaction is more native in the sense of jointly modeling two modalities for the image segmentation task, and we propose convolutional multimodal LSTM to encode the sequential interactions between individual words, visual information, and spatial information. We sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07939","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vkDLbZ5ZNJONDbvT70w2RIEqnWLyooBkNSPH2BrDILlrfYjo4bzazdRBA29j0HsP3RrN/gzu3w1InTkVlVkEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:39:22.902302Z"},"content_sha256":"bc2e4fbff58d59160ee43392751b0a8ba6df09248ac98a4e1ac3ebaf1c79b838","schema_version":"1.0","event_id":"sha256:bc2e4fbff58d59160ee43392751b0a8ba6df09248ac98a4e1ac3ebaf1c79b838"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VKNGJ2B624RTXFN3ZEEHCQDFES/bundle.json","state_url":"https://pith.science/pith/VKNGJ2B624RTXFN3ZEEHCQDFES/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VKNGJ2B624RTXFN3ZEEHCQDFES/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T08:39:22Z","links":{"resolver":"https://pith.science/pith/VKNGJ2B624RTXFN3ZEEHCQDFES","bundle":"https://pith.science/pith/VKNGJ2B624RTXFN3ZEEHCQDFES/bundle.json","state":"https://pith.science/pith/VKNGJ2B624RTXFN3ZEEHCQDFES/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VKNGJ2B624RTXFN3ZEEHCQDFES/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VKNGJ2B624RTXFN3ZEEHCQDFES","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"646ffd1dee9e63b62cc471efa3bd11ccb43805dc58a58bf3aa1b5a4bd8273028","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T05:22:22Z","title_canon_sha256":"79039e69298b348ec4db8f442d23b869bbea26b418c36a25afec2f2320de733e"},"schema_version":"1.0","source":{"id":"1703.07939","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07939","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07939v2","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07939","created_at":"2026-05-18T00:38:35Z"},{"alias_kind":"pith_short_12","alias_value":"VKNGJ2B624RT","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VKNGJ2B624RTXFN3","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VKNGJ2B6","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:bc2e4fbff58d59160ee43392751b0a8ba6df09248ac98a4e1ac3ebaf1c79b838","target":"graph","created_at":"2026-05-18T00:38:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment images by combining these two types of representations. We argue that learning word-to-image interaction is more native in the sense of jointly modeling two modalities for the image segmentation task, and we propose convolutional multimodal LSTM to encode the sequential interactions between individual words, visual information, and spatial information. We sho","authors_text":"Alan Yuille, Chenxi Liu, Jimei Yang, Xiaohui Shen, Xin Lu, Zhe Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T05:22:22Z","title":"Recurrent Multimodal Interaction for Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07939","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0912e9809fdc704b7bcfdab2b19fb0b4375cb5db224863709f8e145a79615f0a","target":"record","created_at":"2026-05-18T00:38:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"646ffd1dee9e63b62cc471efa3bd11ccb43805dc58a58bf3aa1b5a4bd8273028","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-23T05:22:22Z","title_canon_sha256":"79039e69298b348ec4db8f442d23b869bbea26b418c36a25afec2f2320de733e"},"schema_version":"1.0","source":{"id":"1703.07939","kind":"arxiv","version":2}},"canonical_sha256":"aa9a64e83ed7233b95bbc9087140652496a20ace6e26fb515c13ddfa2ba3fa28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa9a64e83ed7233b95bbc9087140652496a20ace6e26fb515c13ddfa2ba3fa28","first_computed_at":"2026-05-18T00:38:35.873908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:35.873908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A1eo38biPTEkL2nw6crPyCYBy6g6tFR5e0WELrf9IoevW1LUNm3NsYcgCjJtPUPzMp7Sd+OK+KEWaurDbSetDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:35.874309Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.07939","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0912e9809fdc704b7bcfdab2b19fb0b4375cb5db224863709f8e145a79615f0a","sha256:bc2e4fbff58d59160ee43392751b0a8ba6df09248ac98a4e1ac3ebaf1c79b838"],"state_sha256":"aee9c02d20d0c5b13965f780e1a497a3e53c5c14e3b242d2fa95b16d4a80350e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+mrjA+mR6/F5ZSnyVP9PvaKccDGiqhl5VrkR/UZnt8JCBZhj4s7Z6SKzP6kVsahFFb6He89gKDfQGPnRk4t+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:39:22.904930Z","bundle_sha256":"59b7d04cd8ee3254bcf52f77e3b8d9df36cce1cafebb047038b554aa63744983"}}